rcu-tasks: Initialize data to eliminate RCU-tasks/do_exit() deadlocks

Holding a mutex across synchronize_rcu_tasks() and acquiring
that same mutex in code called from do_exit() after its call to
exit_tasks_rcu_start() but before its call to exit_tasks_rcu_stop()
results in deadlock.  This is by design, because tasks that are far
enough into do_exit() are no longer present on the tasks list, making
it a bit difficult for RCU Tasks to find them, let alone wait on them
to do a voluntary context switch.  However, such deadlocks are becoming
more frequent.  In addition, lockdep currently does not detect such
deadlocks and they can be difficult to reproduce.

In addition, if a task voluntarily context switches during that time
(for example, if it blocks acquiring a mutex), then this task is in an
RCU Tasks quiescent state.  And with some adjustments, RCU Tasks could
just as well take advantage of that fact.

This commit therefore initializes the data structures that will be needed
to rely on these quiescent states and to eliminate these deadlocks.

Link: https://lore.kernel.org/all/20240118021842.290665-1-chenzhongjin@huawei.com/
Reported-by: Chen Zhongjin <chenzhongjin@huawei.com>
Reported-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Yang Jihong <yangjihong1@huawei.com>
Tested-by: Chen Zhongjin <chenzhongjin@huawei.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>

diff --git a/init/init_task.c b/init/init_task.c
index 7ecb458eb3da60eb73123f4b2072910f194c4bb5..4daee6d761c86c11bcfe76b04a137d7f0ea38ec9 100644 (file)
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -147,6 +147,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
        .rcu_tasks_holdout = false,
        .rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
        .rcu_tasks_idle_cpu = -1,
+       .rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
 #endif
 #ifdef CONFIG_TASKS_TRACE_RCU
        .trc_reader_nesting = 0,

diff --git a/kernel/fork.c b/kernel/fork.c
index 0d944e92a43ffa13bdbcce6c6a28c44bab29ca19..af7203be1d2d199cd3184deb265ba36a72e6567c 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1976,6 +1976,7 @@ static inline void rcu_copy_process(struct task_struct *p)
        p->rcu_tasks_holdout = false;
        INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
        p->rcu_tasks_idle_cpu = -1;
+       INIT_LIST_HEAD(&p->rcu_tasks_exit_list);
 #endif /* #ifdef CONFIG_TASKS_RCU */
 #ifdef CONFIG_TASKS_TRACE_RCU
        p->trc_reader_nesting = 0;

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 6961a1b5b7835f5fe99da251b77d83343c28eeb0..edd14fee48c5c32c375c017e07f6735c6af2d3b4 100644 (file)
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -274,6 +274,8 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
                rtpcp->rtpp = rtp;
                if (!rtpcp->rtp_blkd_tasks.next)
                        INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
+               if (!rtpcp->rtp_exit_list.next)
+                       INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
        }
 
        pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,